Efficient identification, localization and quantification of grapevine inflorescences in unprepared field images using Fully Convolutional Networks.
Robert RudolphKatja HerzogReinhard TöpferVolker SteinhagePublished in: CoRR (2018)
Keyphrases
- three dimensional
- image data
- image analysis
- image database
- ground truth
- object recognition
- test images
- image registration
- input image
- rigid body
- image features
- image regions
- edge detection
- similarity measure
- multiple images
- identification rate
- feature points
- computer graphics
- segmentation method
- segmentation algorithm
- image classification
- image collections
- object detection
- high resolution
- object localization
- deep learning
- localization method
- image retrieval
- accurate localization
- convolutional network